© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 15-LLAMASCOPE-RES-131K
    11. 27046
    Prev
    Next
    INDEX
    Explanations

    terms related to possession and ownership of weapons or illegal items

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    683
    -0.08
    ileo
    -0.08
    877
    -0.08
    682
    -0.07
    umas
    -0.07
    jej
    -0.07
    .FLOAT
    -0.06
    .ml
    -0.06
    äll
    -0.06
    -strokes
    -0.06
    POSITIVE LOGITS
    ,class
    0.07
    è§
    0.07
     ansch
    0.07
     Bernardino
    0.06
     Class
    0.06
     Tob
    0.06
    ãģ¡ãģ¯
    0.06
    hold
    0.06
     Ton
    0.06
     uncert
    0.06
    Activations Density 0.002%

    No Known Activations